No abstract

Sentence word segmentation is an important task in robust part-of-speech (POS) tagging systems. In some cases this is relatively simple, since each textual word (or token) corresponds to one linguistic component. However, there are many others where segmentation can be very hard, such as those of contractions, verbal forms with enclitic pronouns, etc., where the same token contains information about two or more linguistic components. There are two main approaches to solving these difficult cases: This paper results from a project developed at Centro Ramón Piñeiro para a Investigación en Humanidades and is partially supported by Ministerio de Educación y Ciencia (TIN2004-07246-C03-01), Xunta de Galicia (PGIDIT05PXIC30501PN) and Universidade de Vigo.